staticinlinevoid sanity_check_pinned_pages(struct page **pages, unsignedlong npages)
{ if (!IS_ENABLED(CONFIG_DEBUG_VM)) return;
/* * We only pin anonymous pages if they are exclusive. Once pinned, we * can no longer turn them possibly shared and PageAnonExclusive() will * stick around until the page is freed. * * We'd like to verify that our pinned anonymous pages are still mapped * exclusively. The issue with anon THP is that we don't know how * they are/were mapped when pinning them. However, for anon * THP we can assume that either the given page (PTE-mapped THP) or * the head page (PMD-mapped THP) should be PageAnonExclusive(). If * neither is the case, there is certainly something wrong.
*/ for (; npages; npages--, pages++) { struct page *page = *pages; struct folio *folio;
if (!page) continue;
folio = page_folio(page);
if (is_zero_page(page) ||
!folio_test_anon(folio)) continue; if (!folio_test_large(folio) || folio_test_hugetlb(folio))
VM_WARN_ON_ONCE_FOLIO(!PageAnonExclusive(&folio->page), folio); else /* Either a PTE-mapped or a PMD-mapped THP. */
VM_WARN_ON_ONCE_PAGE(!PageAnonExclusive(&folio->page) &&
!PageAnonExclusive(page), page);
}
}
/* * Return the folio with ref appropriately incremented, * or NULL if that failed.
*/ staticinlinestruct folio *try_get_folio(struct page *page, int refs)
{ struct folio *folio;
retry:
folio = page_folio(page); if (WARN_ON_ONCE(folio_ref_count(folio) < 0)) return NULL; if (unlikely(!folio_ref_try_add(folio, refs))) return NULL;
/* * At this point we have a stable reference to the folio; but it * could be that between calling page_folio() and the refcount * increment, the folio was split, in which case we'd end up * holding a reference on a folio that has nothing to do with the page * we were given anymore. * So now that the folio is stable, recheck that the page still * belongs to this folio.
*/ if (unlikely(page_folio(page) != folio)) {
folio_put_refs(folio, refs); goto retry;
}
return folio;
}
staticvoid gup_put_folio(struct folio *folio, int refs, unsignedint flags)
{ if (flags & FOLL_PIN) { if (is_zero_folio(folio)) return;
node_stat_mod_folio(folio, NR_FOLL_PIN_RELEASED, refs); if (folio_has_pincount(folio))
atomic_sub(refs, &folio->_pincount); else
refs *= GUP_PIN_COUNTING_BIAS;
}
folio_put_refs(folio, refs);
}
/** * try_grab_folio() - add a folio's refcount by a flag-dependent amount * @folio: pointer to folio to be grabbed * @refs: the value to (effectively) add to the folio's refcount * @flags: gup flags: these are the FOLL_* flag values * * This might not do anything at all, depending on the flags argument. * * "grab" names in this file mean, "look at flags to decide whether to use * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. * * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same * time. * * Return: 0 for success, or if no action was required (if neither FOLL_PIN * nor FOLL_GET was set, nothing is done). A negative error code for failure: * * -ENOMEM FOLL_GET or FOLL_PIN was set, but the folio could not * be grabbed. * * It is called when we have a stable reference for the folio, typically in * GUP slow path.
*/ int __must_check try_grab_folio(struct folio *folio, int refs, unsignedint flags)
{ if (WARN_ON_ONCE(folio_ref_count(folio) <= 0)) return -ENOMEM;
if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(&folio->page))) return -EREMOTEIO;
if (flags & FOLL_GET)
folio_ref_add(folio, refs); elseif (flags & FOLL_PIN) { /* * Don't take a pin on the zero page - it's not going anywhere * and it is used in a *lot* of places.
*/ if (is_zero_folio(folio)) return 0;
/* * Increment the normal page refcount field at least once, * so that the page really is pinned.
*/ if (folio_has_pincount(folio)) {
folio_ref_add(folio, refs);
atomic_add(refs, &folio->_pincount);
} else {
folio_ref_add(folio, refs * GUP_PIN_COUNTING_BIAS);
}
/** * unpin_user_page() - release a dma-pinned page * @page: pointer to page to be released * * Pages that were pinned via pin_user_pages*() must be released via either * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so * that such pages can be separately tracked and uniquely handled. In * particular, interactions with RDMA and filesystems need special handling.
*/ void unpin_user_page(struct page *page)
{
sanity_check_pinned_pages(&page, 1);
gup_put_folio(page_folio(page), 1, FOLL_PIN);
}
EXPORT_SYMBOL(unpin_user_page);
/** * unpin_folio() - release a dma-pinned folio * @folio: pointer to folio to be released * * Folios that were pinned via memfd_pin_folios() or other similar routines * must be released either using unpin_folio() or unpin_folios().
*/ void unpin_folio(struct folio *folio)
{
gup_put_folio(folio, 1, FOLL_PIN);
}
EXPORT_SYMBOL_GPL(unpin_folio);
/** * folio_add_pin - Try to get an additional pin on a pinned folio * @folio: The folio to be pinned * * Get an additional pin on a folio we already have a pin on. Makes no change * if the folio is a zero_page.
*/ void folio_add_pin(struct folio *folio)
{ if (is_zero_folio(folio)) return;
/* * Similar to try_grab_folio(): be sure to *also* increment the normal * page refcount field at least once, so that the page really is * pinned.
*/ if (folio_has_pincount(folio)) {
WARN_ON_ONCE(atomic_read(&folio->_pincount) < 1);
folio_ref_inc(folio);
atomic_inc(&folio->_pincount);
} else {
WARN_ON_ONCE(folio_ref_count(folio) < GUP_PIN_COUNTING_BIAS);
folio_ref_add(folio, GUP_PIN_COUNTING_BIAS);
}
}
for (nr = i + 1; nr < npages; nr++) { if (page_folio(list[nr]) != folio) break;
}
*ntails = nr - i; return folio;
}
/** * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages * @pages: array of pages to be maybe marked dirty, and definitely released. * @npages: number of pages in the @pages array. * @make_dirty: whether to mark the pages dirty * * "gup-pinned page" refers to a page that has had one of the get_user_pages() * variants called on that page. * * For each page in the @pages array, make that page (or its head page, if a * compound page) dirty, if @make_dirty is true, and if the page was previously * listed as clean. In any case, releases all pages using unpin_user_page(), * possibly via unpin_user_pages(), for the non-dirty case. * * Please see the unpin_user_page() documentation for details. * * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is * required, then the caller should a) verify that this is really correct, * because _lock() is usually required, and b) hand code it: * set_page_dirty_lock(), unpin_user_page(). *
*/ void unpin_user_pages_dirty_lock(struct page **pages, unsignedlong npages, bool make_dirty)
{ unsignedlong i; struct folio *folio; unsignedint nr;
if (!make_dirty) {
unpin_user_pages(pages, npages); return;
}
sanity_check_pinned_pages(pages, npages); for (i = 0; i < npages; i += nr) {
folio = gup_folio_next(pages, npages, i, &nr); /* * Checking PageDirty at this point may race with * clear_page_dirty_for_io(), but that's OK. Two key * cases: * * 1) This code sees the page as already dirty, so it * skips the call to set_page_dirty(). That could happen * because clear_page_dirty_for_io() called * folio_mkclean(), followed by set_page_dirty(). * However, now the page is going to get written back, * which meets the original intention of setting it * dirty, so all is well: clear_page_dirty_for_io() goes * on to call TestClearPageDirty(), and write the page * back. * * 2) This code sees the page as clean, so it calls * set_page_dirty(). The page stays dirty, despite being * written back, so it gets written back again in the * next writeback cycle. This is harmless.
*/ if (!folio_test_dirty(folio)) {
folio_lock(folio);
folio_mark_dirty(folio);
folio_unlock(folio);
}
gup_put_folio(folio, nr, FOLL_PIN);
}
}
EXPORT_SYMBOL(unpin_user_pages_dirty_lock);
/** * unpin_user_page_range_dirty_lock() - release and optionally dirty * gup-pinned page range * * @page: the starting page of a range maybe marked dirty, and definitely released. * @npages: number of consecutive pages to release. * @make_dirty: whether to mark the pages dirty * * "gup-pinned page range" refers to a range of pages that has had one of the * pin_user_pages() variants called on that page. * * For the page ranges defined by [page .. page+npages], make that range (or * its head pages, if a compound page) dirty, if @make_dirty is true, and if the * page range was previously listed as clean. * * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is * required, then the caller should a) verify that this is really correct, * because _lock() is usually required, and b) hand code it: * set_page_dirty_lock(), unpin_user_page(). *
*/ void unpin_user_page_range_dirty_lock(struct page *page, unsignedlong npages, bool make_dirty)
{ unsignedlong i; struct folio *folio; unsignedint nr;
for (i = 0; i < npages; i += nr) {
folio = gup_folio_range_next(page, npages, i, &nr); if (make_dirty && !folio_test_dirty(folio)) {
folio_lock(folio);
folio_mark_dirty(folio);
folio_unlock(folio);
}
gup_put_folio(folio, nr, FOLL_PIN);
}
}
EXPORT_SYMBOL(unpin_user_page_range_dirty_lock);
/* * Don't perform any sanity checks because we might have raced with * fork() and some anonymous pages might now actually be shared -- * which is why we're unpinning after all.
*/ for (i = 0; i < npages; i += nr) {
folio = gup_folio_next(pages, npages, i, &nr);
gup_put_folio(folio, nr, FOLL_PIN);
}
}
/** * unpin_user_pages() - release an array of gup-pinned pages. * @pages: array of pages to be marked dirty and released. * @npages: number of pages in the @pages array. * * For each page in the @pages array, release the page using unpin_user_page(). * * Please see the unpin_user_page() documentation for details.
*/ void unpin_user_pages(struct page **pages, unsignedlong npages)
{ unsignedlong i; struct folio *folio; unsignedint nr;
/* * If this WARN_ON() fires, then the system *might* be leaking pages (by * leaving them pinned), but probably not. More likely, gup/pup returned * a hard -ERRNO error to the caller, who erroneously passed it here.
*/ if (WARN_ON(IS_ERR_VALUE(npages))) return;
sanity_check_pinned_pages(pages, npages); for (i = 0; i < npages; i += nr) { if (!pages[i]) {
nr = 1; continue;
}
folio = gup_folio_next(pages, npages, i, &nr);
gup_put_folio(folio, nr, FOLL_PIN);
}
}
EXPORT_SYMBOL(unpin_user_pages);
/** * unpin_user_folio() - release pages of a folio * @folio: pointer to folio to be released * @npages: number of pages of same folio * * Release npages of the folio
*/ void unpin_user_folio(struct folio *folio, unsignedlong npages)
{
gup_put_folio(folio, npages, FOLL_PIN);
}
EXPORT_SYMBOL(unpin_user_folio);
/** * unpin_folios() - release an array of gup-pinned folios. * @folios: array of folios to be marked dirty and released. * @nfolios: number of folios in the @folios array. * * For each folio in the @folios array, release the folio using gup_put_folio. * * Please see the unpin_folio() documentation for details.
*/ void unpin_folios(struct folio **folios, unsignedlong nfolios)
{ unsignedlong i = 0, j;
/* * If this WARN_ON() fires, then the system *might* be leaking folios * (by leaving them pinned), but probably not. More likely, gup/pup * returned a hard -ERRNO error to the caller, who erroneously passed * it here.
*/ if (WARN_ON(IS_ERR_VALUE(nfolios))) return;
while (i < nfolios) { for (j = i + 1; j < nfolios; j++) if (folios[i] != folios[j]) break;
if (folios[i])
gup_put_folio(folios[i], j - i, FOLL_PIN);
i = j;
}
}
EXPORT_SYMBOL_GPL(unpin_folios);
/* * Set the MMF_HAS_PINNED if not set yet; after set it'll be there for the mm's * lifecycle. Avoid setting the bit unless necessary, or it might cause write * cache bouncing on large SMP machines for concurrent pinned gups.
*/ staticinlinevoid mm_set_has_pinned_flag(unsignedlong *mm_flags)
{ if (!test_bit(MMF_HAS_PINNED, mm_flags))
set_bit(MMF_HAS_PINNED, mm_flags);
}
/** * try_grab_folio_fast() - Attempt to get or pin a folio in fast path. * @page: pointer to page to be grabbed * @refs: the value to (effectively) add to the folio's refcount * @flags: gup flags: these are the FOLL_* flag values. * * "grab" names in this file mean, "look at flags to decide whether to use * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. * * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the * same time. (That's true throughout the get_user_pages*() and * pin_user_pages*() APIs.) Cases: * * FOLL_GET: folio's refcount will be incremented by @refs. * * FOLL_PIN on large folios: folio's refcount will be incremented by * @refs, and its pincount will be incremented by @refs. * * FOLL_PIN on single-page folios: folio's refcount will be incremented by * @refs * GUP_PIN_COUNTING_BIAS. * * Return: The folio containing @page (with refcount appropriately * incremented) for success, or NULL upon failure. If neither FOLL_GET * nor FOLL_PIN was set, that's considered failure, and furthermore, * a likely bug in the caller, so a warning is also emitted. * * It uses add ref unless zero to elevate the folio refcount and must be called * in fast path only.
*/ staticstruct folio *try_grab_folio_fast(struct page *page, int refs, unsignedint flags)
{ struct folio *folio;
/* Raise warn if it is not called in fast GUP */
VM_WARN_ON_ONCE(!irqs_disabled());
if (WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == 0)) return NULL;
if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) return NULL;
if (flags & FOLL_GET) return try_get_folio(page, refs);
/* FOLL_PIN is set */
/* * Don't take a pin on the zero page - it's not going anywhere * and it is used in a *lot* of places.
*/ if (is_zero_page(page)) return page_folio(page);
folio = try_get_folio(page, refs); if (!folio) return NULL;
/* * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a * right zone, so fail and let the caller fall back to the slow * path.
*/ if (unlikely((flags & FOLL_LONGTERM) &&
!folio_is_longterm_pinnable(folio))) {
folio_put_refs(folio, refs); return NULL;
}
/* * When pinning a large folio, use an exact count to track it. * * However, be sure to *also* increment the normal folio * refcount field at least once, so that the folio really * is pinned. That's why the refcount from the earlier * try_get_folio() is left intact.
*/ if (folio_has_pincount(folio))
atomic_add(refs, &folio->_pincount); else
folio_ref_add(folio,
refs * (GUP_PIN_COUNTING_BIAS - 1)); /* * Adjust the pincount before re-checking the PTE for changes. * This is essentially a smp_mb() and is paired with a memory * barrier in folio_try_share_anon_rmap_*().
*/
smp_mb__after_atomic();
/* Common code for can_follow_write_* */ staticinlinebool can_follow_write_common(struct page *page, struct vm_area_struct *vma, unsignedint flags)
{ /* Maybe FOLL_FORCE is set to override it? */ if (!(flags & FOLL_FORCE)) returnfalse;
/* But FOLL_FORCE has no effect on shared mappings */ if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) returnfalse;
/* ... or read-only private ones */ if (!(vma->vm_flags & VM_MAYWRITE)) returnfalse;
/* ... or already writable ones that just need to take a write fault */ if (vma->vm_flags & VM_WRITE) returnfalse;
/* * See can_change_pte_writable(): we broke COW and could map the page * writable if we have an exclusive anonymous page ...
*/ return page && PageAnon(page) && PageAnonExclusive(page);
}
/* * When core dumping, we don't want to allocate unnecessary pages or * page tables. Return error instead of NULL to skip handle_mm_fault, * then get_dump_page() will return NULL to leave a hole in the dump. * But we can only make this optimization where a hole would surely * be zero-filled if handle_mm_fault() actually did handle it.
*/ if (is_vm_hugetlb_page(vma)) { struct hstate *h = hstate_vma(vma);
#ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES /* FOLL_FORCE can write to even unwritable PUDs in COW mappings. */ staticinlinebool can_follow_write_pud(pud_t pud, struct page *page, struct vm_area_struct *vma, unsignedint flags)
{ /* If the pud is writable, we can write to the page. */ if (pud_write(pud)) returntrue;
if (!pud_write(pud) && gup_must_unshare(vma, flags, page)) return ERR_PTR(-EMLINK);
ret = try_grab_folio(page_folio(page), 1, flags); if (ret)
page = ERR_PTR(ret); else
ctx->page_mask = HPAGE_PUD_NR - 1;
return page;
}
/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */ staticinlinebool can_follow_write_pmd(pmd_t pmd, struct page *page, struct vm_area_struct *vma, unsignedint flags)
{ /* If the pmd is writable, we can write to the page. */ if (pmd_write(pmd)) returntrue;
if (!can_follow_write_common(page, vma, flags)) returnfalse;
/* ... and a write-fault isn't required for other reasons. */ if (pmd_needs_soft_dirty_wp(vma, pmd)) returnfalse; return !userfaultfd_huge_pmd_wp(vma, pmd);
}
/* Proper page table entry exists, but no corresponding struct page */ return -EEXIST;
}
/* FOLL_FORCE can write to even unwritable PTEs in COW mappings. */ staticinlinebool can_follow_write_pte(pte_t pte, struct page *page, struct vm_area_struct *vma, unsignedint flags)
{ /* If the pte is writable, we can write to the page. */ if (pte_write(pte)) returntrue;
if (!can_follow_write_common(page, vma, flags)) returnfalse;
/* ... and a write-fault isn't required for other reasons. */ if (pte_needs_soft_dirty_wp(vma, pte)) returnfalse; return !userfaultfd_pte_wp(vma, pte);
}
ptep = pte_offset_map_lock(mm, pmd, address, &ptl); if (!ptep) return no_page_table(vma, flags, address);
pte = ptep_get(ptep); if (!pte_present(pte)) goto no_page; if (pte_protnone(pte) && !gup_can_follow_protnone(vma, flags)) goto no_page;
page = vm_normal_page(vma, address, pte);
/* * We only care about anon pages in can_follow_write_pte().
*/ if ((flags & FOLL_WRITE) &&
!can_follow_write_pte(pte, page, vma, flags)) {
page = NULL; goto out;
}
if (unlikely(!page)) { if (flags & FOLL_DUMP) { /* Avoid special (like zero) pages in core dumps */
page = ERR_PTR(-EFAULT); goto out;
}
/* try_grab_folio() does nothing unless FOLL_GET or FOLL_PIN is set. */
ret = try_grab_folio(folio, 1, flags); if (unlikely(ret)) {
page = ERR_PTR(ret); goto out;
}
/* * We need to make the page accessible if and only if we are going * to access its content (the FOLL_PIN case). Please see * Documentation/core-api/pin_user_pages.rst for details.
*/ if (flags & FOLL_PIN) {
ret = arch_make_folio_accessible(folio); if (ret) {
unpin_user_page(page);
page = ERR_PTR(ret); goto out;
}
} if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) &&
!pte_dirty(pte) && !folio_test_dirty(folio))
folio_mark_dirty(folio); /* * pte_mkyoung() would be more correct here, but atomic care * is needed to avoid losing the dirty bit: it is easier to use * folio_mark_accessed().
*/
folio_mark_accessed(folio);
}
out:
pte_unmap_unlock(ptep, ptl); return page;
no_page:
pte_unmap_unlock(ptep, ptl); if (!pte_none(pte)) return NULL; return no_page_table(vma, flags, address);
}
/** * follow_page_mask - look up a page descriptor from a user-virtual address * @vma: vm_area_struct mapping @address * @address: virtual address to look up * @flags: flags modifying lookup behaviour * @ctx: contains dev_pagemap for %ZONE_DEVICE memory pinning and a * pointer to output page_mask * * @flags can have FOLL_ flags set, defined in <linux/mm.h> * * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches * the device's dev_pagemap metadata to avoid repeating expensive lookups. * * When getting an anonymous page and the caller has to trigger unsharing * of a shared anonymous page first, -EMLINK is returned. The caller should * trigger a fault with FAULT_FLAG_UNSHARE set. Note that unsharing is only * relevant with FOLL_PIN and !FOLL_WRITE. * * On output, the @ctx->page_mask is set according to the size of the page. * * Return: the mapped (struct page *), %NULL if no mapping exists, or * an error pointer if there is a mapping to something not represented * by a page descriptor (see also vm_normal_page()).
*/ staticstruct page *follow_page_mask(struct vm_area_struct *vma, unsignedlong address, unsignedint flags, struct follow_page_context *ctx)
{
pgd_t *pgd; struct mm_struct *mm = vma->vm_mm; struct page *page;
/* user gate pages are read-only */ if (gup_flags & FOLL_WRITE) return -EFAULT;
pgd = pgd_offset(mm, address); if (pgd_none(*pgd)) return -EFAULT;
p4d = p4d_offset(pgd, address); if (p4d_none(*p4d)) return -EFAULT;
pud = pud_offset(p4d, address); if (pud_none(*pud)) return -EFAULT;
pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) return -EFAULT;
pte = pte_offset_map(pmd, address); if (!pte) return -EFAULT;
entry = ptep_get(pte); if (pte_none(entry)) goto unmap;
*vma = get_gate_vma(mm); if (!page) goto out;
*page = vm_normal_page(*vma, address, entry); if (!*page) { if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(entry))) goto unmap;
*page = pte_page(entry);
}
ret = try_grab_folio(page_folio(*page), 1, gup_flags); if (unlikely(ret)) goto unmap;
out:
ret = 0;
unmap:
pte_unmap(pte); return ret;
}
/* * mmap_lock must be held on entry. If @flags has FOLL_UNLOCKABLE but not * FOLL_NOWAIT, the mmap_lock may be released. If it is, *@locked will be set * to 0 and -EBUSY returned.
*/ staticint faultin_page(struct vm_area_struct *vma, unsignedlong address, unsignedint flags, bool unshare, int *locked)
{ unsignedint fault_flags = 0;
vm_fault_t ret;
if (flags & FOLL_NOFAULT) return -EFAULT; if (flags & FOLL_WRITE)
fault_flags |= FAULT_FLAG_WRITE; if (flags & FOLL_REMOTE)
fault_flags |= FAULT_FLAG_REMOTE; if (flags & FOLL_UNLOCKABLE) {
fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; /* * FAULT_FLAG_INTERRUPTIBLE is opt-in. GUP callers must set * FOLL_INTERRUPTIBLE to enable FAULT_FLAG_INTERRUPTIBLE. * That's because some callers may not be prepared to * handle early exits caused by non-fatal signals.
*/ if (flags & FOLL_INTERRUPTIBLE)
fault_flags |= FAULT_FLAG_INTERRUPTIBLE;
} if (flags & FOLL_NOWAIT)
fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT; if (flags & FOLL_TRIED) { /* * Note: FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_TRIED * can co-exist
*/
fault_flags |= FAULT_FLAG_TRIED;
} if (unshare) {
fault_flags |= FAULT_FLAG_UNSHARE; /* FAULT_FLAG_WRITE and FAULT_FLAG_UNSHARE are incompatible */
VM_WARN_ON_ONCE(fault_flags & FAULT_FLAG_WRITE);
}
ret = handle_mm_fault(vma, address, fault_flags, NULL);
if (ret & VM_FAULT_COMPLETED) { /* * With FAULT_FLAG_RETRY_NOWAIT we'll never release the * mmap lock in the page fault handler. Sanity check this.
*/
WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT);
*locked = 0;
/* * We should do the same as VM_FAULT_RETRY, but let's not * return -EBUSY since that's not reflecting the reality of * what has happened - we've just fully completed a page * fault, with the mmap lock released. Use -EAGAIN to show * that we want to take the mmap lock _again_.
*/ return -EAGAIN;
}
if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, flags);
if (err) return err;
BUG();
}
if (ret & VM_FAULT_RETRY) { if (!(fault_flags & FAULT_FLAG_RETRY_NOWAIT))
*locked = 0; return -EBUSY;
}
return 0;
}
/* * Writing to file-backed mappings which require folio dirty tracking using GUP * is a fundamentally broken operation, as kernel write access to GUP mappings * do not adhere to the semantics expected by a file system. * * Consider the following scenario:- * * 1. A folio is written to via GUP which write-faults the memory, notifying * the file system and dirtying the folio. * 2. Later, writeback is triggered, resulting in the folio being cleaned and * the PTE being marked read-only. * 3. The GUP caller writes to the folio, as it is mapped read/write via the * direct mapping. * 4. The GUP caller, now done with the page, unpins it and sets it dirty * (though it does not have to). * * This results in both data being written to a folio without writenotify, and * the folio being dirtied unexpectedly (if the caller decides to do so).
*/ staticbool writable_file_mapping_allowed(struct vm_area_struct *vma, unsignedlong gup_flags)
{ /* * If we aren't pinning then no problematic write can occur. A long term * pin is the most egregious case so this is the case we disallow.
*/ if ((gup_flags & (FOLL_PIN | FOLL_LONGTERM)) !=
(FOLL_PIN | FOLL_LONGTERM)) returntrue;
/* * If the VMA does not require dirty tracking then no problematic write * can occur either.
*/ return !vma_needs_dirty_tracking(vma);
}
if (vm_flags & (VM_IO | VM_PFNMAP)) return -EFAULT;
if ((gup_flags & FOLL_ANON) && !vma_anon) return -EFAULT;
if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma)) return -EOPNOTSUPP;
if ((gup_flags & FOLL_SPLIT_PMD) && is_vm_hugetlb_page(vma)) return -EOPNOTSUPP;
if (vma_is_secretmem(vma)) return -EFAULT;
if (write) { if (!vma_anon &&
!writable_file_mapping_allowed(vma, gup_flags)) return -EFAULT;
if (!(vm_flags & VM_WRITE) || (vm_flags & VM_SHADOW_STACK)) { if (!(gup_flags & FOLL_FORCE)) return -EFAULT; /* * We used to let the write,force case do COW in a * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could * set a breakpoint in a read-only mapping of an * executable, without corrupting the file (yet only * when that file had been opened for writing!). * Anon pages in shared mappings are surprising: now * just reject it.
*/ if (!is_cow_mapping(vm_flags)) return -EFAULT;
}
} elseif (!(vm_flags & VM_READ)) { if (!(gup_flags & FOLL_FORCE)) return -EFAULT; /* * Is there actually any vma we can reach here which does not * have VM_MAYREAD set?
*/ if (!(vm_flags & VM_MAYREAD)) return -EFAULT;
} /* * gups are always data accesses, not instruction * fetches, so execute=false here
*/ if (!arch_vma_access_permitted(vma, write, false, foreign)) return -EFAULT; return 0;
}
/* * This is "vma_lookup()", but with a warning if we would have * historically expanded the stack in the GUP code.
*/ staticstruct vm_area_struct *gup_vma_lookup(struct mm_struct *mm, unsignedlong addr)
{ #ifdef CONFIG_STACK_GROWSUP return vma_lookup(mm, addr); #else staticvolatileunsignedlong next_warn; struct vm_area_struct *vma; unsignedlong now, next;
/* Only warn for half-way relevant accesses */ if (!(vma->vm_flags & VM_GROWSDOWN)) return NULL; if (vma->vm_start - addr > 65536) return NULL;
/* Let's not warn more than once an hour.. */
now = jiffies; next = next_warn; if (next && time_before(now, next)) return NULL;
next_warn = now + 60*60*HZ;
/* Let people know things may have changed. */
pr_warn("GUP no longer grows the stack in %s (%d): %lx-%lx (%lx)\n",
current->comm, task_pid_nr(current),
vma->vm_start, vma->vm_end, addr);
dump_stack(); return NULL; #endif
}
/** * __get_user_pages() - pin user pages in memory * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. * @locked: whether we're still with the mmap_lock held * * Returns either number of pages pinned (which may be less than the * number requested), or an error. Details about the return value: * * -- If nr_pages is 0, returns 0. * -- If nr_pages is >0, but no pages were pinned, returns -errno. * -- If nr_pages is >0, and some pages were pinned, returns the number of * pages pinned. Again, this may be less than nr_pages. * -- 0 return value is possible when the fault would need to be retried. * * The caller is responsible for releasing returned @pages, via put_page(). * * Must be called with mmap_lock held. It may be released. See below. * * __get_user_pages walks a process's page tables and takes a reference to * each struct page that each user address corresponds to at a given * instant. That is, it takes the page that would be accessed if a user * thread accesses the given user virtual address at that instant. * * This does not guarantee that the page exists in the user mappings when * __get_user_pages returns, and there may even be a completely different * page there in some cases (eg. if mmapped pagecache has been invalidated * and subsequently re-faulted). However it does guarantee that the page * won't be freed completely. And mostly callers simply care that the page * contains data that was valid *at some point in time*. Typically, an IO * or similar operation cannot guarantee anything stronger anyway because * locks can't be held over the syscall boundary. * * If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If * the page is written to, set_page_dirty (or set_page_dirty_lock, as * appropriate) must be called after the page is finished with, and * before put_page is called. * * If FOLL_UNLOCKABLE is set without FOLL_NOWAIT then the mmap_lock may * be released. If this happens *@locked will be set to 0 on return. * * A caller using such a combination of @gup_flags must therefore hold the * mmap_lock for reading only, and recognize when it's been released. Otherwise, * it must be held for either reading or writing and will not be released. * * In most cases, get_user_pages or get_user_pages_fast should be used * instead of __get_user_pages. __get_user_pages should be used only if * you need some special @gup_flags.
*/ staticlong __get_user_pages(struct mm_struct *mm, unsignedlong start, unsignedlong nr_pages, unsignedint gup_flags, struct page **pages, int *locked)
{ long ret = 0, i = 0; struct vm_area_struct *vma = NULL; struct follow_page_context ctx = { NULL };
/* FOLL_GET and FOLL_PIN are mutually exclusive. */
VM_WARN_ON_ONCE((gup_flags & (FOLL_PIN | FOLL_GET)) ==
(FOLL_PIN | FOLL_GET));
do { struct page *page; unsignedint page_increm;
/* first iteration or cross vma bound */ if (!vma || start >= vma->vm_end) { /* * MADV_POPULATE_(READ|WRITE) wants to handle VMA * lookups+error reporting differently.
*/ if (gup_flags & FOLL_MADV_POPULATE) {
vma = vma_lookup(mm, start); if (!vma) {
ret = -ENOMEM; goto out;
} if (check_vma_flags(vma, gup_flags)) {
ret = -EINVAL; goto out;
} goto retry;
}
vma = gup_vma_lookup(mm, start); if (!vma && in_gate_area(mm, start)) {
ret = get_gate_page(mm, start & PAGE_MASK,
gup_flags, &vma,
pages ? &page : NULL); if (ret) goto out;
ctx.page_mask = 0; goto next_page;
}
if (!vma) {
ret = -EFAULT; goto out;
}
ret = check_vma_flags(vma, gup_flags); if (ret) goto out;
}
retry: /* * If we have a pending SIGKILL, don't keep faulting pages and * potentially allocating memory.
*/ if (fatal_signal_pending(current)) {
ret = -EINTR; goto out;
}
cond_resched();
page = follow_page_mask(vma, start, gup_flags, &ctx); if (!page || PTR_ERR(page) == -EMLINK) {
ret = faultin_page(vma, start, gup_flags,
PTR_ERR(page) == -EMLINK, locked); switch (ret) { case 0: goto retry; case -EBUSY: case -EAGAIN:
ret = 0;
fallthrough; case -EFAULT: case -ENOMEM: case -EHWPOISON: goto out;
}
BUG();
} elseif (PTR_ERR(page) == -EEXIST) { /* * Proper page table entry exists, but no corresponding * struct page. If the caller expects **pages to be * filled in, bail out now, because that can't be done * for this page.
*/ if (pages) {
ret = PTR_ERR(page); goto out;
}
} elseif (IS_ERR(page)) {
ret = PTR_ERR(page); goto out;
}
next_page:
page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask); if (page_increm > nr_pages)
page_increm = nr_pages;
if (pages) { struct page *subpage; unsignedint j;
/* * This must be a large folio (and doesn't need to * be the whole folio; it can be part of it), do * the refcount work for all the subpages too. * * NOTE: here the page may not be the head page * e.g. when start addr is not thp-size aligned. * try_grab_folio() should have taken care of tail * pages.
*/ if (page_increm > 1) { struct folio *folio = page_folio(page);
/* * Since we already hold refcount on the * large folio, this should never fail.
*/ if (try_grab_folio(folio, page_increm - 1,
gup_flags)) { /* * Release the 1st page ref if the * folio is problematic, fail hard.
*/
gup_put_folio(folio, 1, gup_flags);
ret = -EFAULT; goto out;
}
}
i += page_increm;
start += page_increm * PAGE_SIZE;
nr_pages -= page_increm;
} while (nr_pages);
out: if (ctx.pgmap)
put_dev_pagemap(ctx.pgmap); return i ? i : ret;
}
/* * The architecture might have a hardware protection * mechanism other than read/write that can deny access. * * gup always represents data access, not instruction * fetches, so execute=false here:
*/ if (!arch_vma_access_permitted(vma, write, false, foreign)) returnfalse;
returntrue;
}
/** * fixup_user_fault() - manually resolve a user page fault * @mm: mm_struct of target mm * @address: user address * @fault_flags:flags to pass down to handle_mm_fault() * @unlocked: did we unlock the mmap_lock while retrying, maybe NULL if caller * does not allow retry. If NULL, the caller must guarantee * that fault_flags does not contain FAULT_FLAG_ALLOW_RETRY. * * This is meant to be called in the specific scenario where for locking reasons * we try to access user memory in atomic context (within a pagefault_disable() * section), this returns -EFAULT, and we want to resolve the user fault before * trying again. * * Typically this is meant to be used by the futex code. * * The main difference with get_user_pages() is that this function will * unconditionally call handle_mm_fault() which will in turn perform all the * necessary SW fixup of the dirty and young bits in the PTE, while * get_user_pages() only guarantees to update these in the struct page. * * This is important for some architectures where those bits also gate the * access permission to the page because they are maintained in software. On * such architectures, gup() will not be enough to make a subsequent access * succeed. * * This function will not return with an unlocked mmap_lock. So it has not the * same semantics wrt the @mm->mmap_lock as does filemap_fault().
*/ int fixup_user_fault(struct mm_struct *mm, unsignedlong address, unsignedint fault_flags, bool *unlocked)
{ struct vm_area_struct *vma;
vm_fault_t ret;
address = untagged_addr_remote(mm, address);
if (unlocked)
fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
retry:
vma = gup_vma_lookup(mm, address); if (!vma) return -EFAULT;
if (!vma_permits_fault(vma, fault_flags)) return -EFAULT;
if ((fault_flags & FAULT_FLAG_KILLABLE) &&
fatal_signal_pending(current)) return -EINTR;
ret = handle_mm_fault(vma, address, fault_flags, NULL);
if (ret & VM_FAULT_COMPLETED) { /* * NOTE: it's a pity that we need to retake the lock here * to pair with the unlock() in the callers. Ideally we * could tell the callers so they do not need to unlock.
*/
mmap_read_lock(mm);
*unlocked = true; return 0;
}
if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0);
/* * GUP always responds to fatal signals. When FOLL_INTERRUPTIBLE is * specified, it'll also respond to generic signals. The caller of GUP * that has FOLL_INTERRUPTIBLE should take care of the GUP interruption.
*/ staticbool gup_signal_pending(unsignedint flags)
{ if (fatal_signal_pending(current)) returntrue;
if (!(flags & FOLL_INTERRUPTIBLE)) returnfalse;
return signal_pending(current);
}
/* * Locking: (*locked == 1) means that the mmap_lock has already been acquired by * the caller. This function may drop the mmap_lock. If it does so, then it will * set (*locked = 0). * * (*locked == 0) means that the caller expects this function to acquire and * drop the mmap_lock. Therefore, the value of *locked will still be zero when * the function returns, even though it may have changed temporarily during * function execution. * * Please note that this function, unlike __get_user_pages(), will not return 0 * for nr_pages > 0, unless FOLL_NOWAIT is used.
*/ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, unsignedlong start, unsignedlong nr_pages, struct page **pages, int *locked, unsignedint flags)
{ long ret, pages_done; bool must_unlock = false;
if (!nr_pages) return 0;
/* * The internal caller expects GUP to manage the lock internally and the * lock must be released when this returns.
*/ if (!*locked) { if (mmap_read_lock_killable(mm)) return -EAGAIN;
must_unlock = true;
*locked = 1;
} else
mmap_assert_locked(mm);
if (flags & FOLL_PIN)
mm_set_has_pinned_flag(&mm->flags);
/* * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior * is to set FOLL_GET if the caller wants pages[] filled in (but has * carelessly failed to specify FOLL_GET), so keep doing that, but only * for FOLL_GET, not for the newer FOLL_PIN. * * FOLL_PIN always expects pages to be non-null, but no need to assert * that here, as any failures will be obvious enough.
*/ if (pages && !(flags & FOLL_PIN))
flags |= FOLL_GET;
pages_done = 0; for (;;) {
ret = __get_user_pages(mm, start, nr_pages, flags, pages,
locked); if (!(flags & FOLL_UNLOCKABLE)) { /* VM_FAULT_RETRY couldn't trigger, bypass */
pages_done = ret; break;
}
/* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */
VM_WARN_ON_ONCE(!*locked && (ret < 0 || ret >= nr_pages));
if (ret > 0) {
nr_pages -= ret;
pages_done += ret; if (!nr_pages) break;
} if (*locked) { /* * VM_FAULT_RETRY didn't trigger or it was a * FOLL_NOWAIT.
*/ if (!pages_done)
pages_done = ret; break;
} /* * VM_FAULT_RETRY triggered, so seek to the faulting offset. * For the prefault case (!pages) we only update counts.
*/ if (likely(pages))
pages += ret;
start += ret << PAGE_SHIFT;
/* The lock was temporarily dropped, so we must unlock later */
must_unlock = true;
retry: /* * Repeat on the address that fired VM_FAULT_RETRY * with both FAULT_FLAG_ALLOW_RETRY and * FAULT_FLAG_TRIED. Note that GUP can be interrupted * by fatal signals of even common signals, depending on * the caller's request. So we need to check it before we * start trying again otherwise it can loop forever.
*/ if (gup_signal_pending(flags)) { if (!pages_done)
pages_done = -EINTR; break;
}
ret = mmap_read_lock_killable(mm); if (ret) { if (!pages_done)
pages_done = ret; break;
}
*locked = 1;
ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED,
pages, locked); if (!*locked) { /* Continue to retry until we succeeded */
VM_WARN_ON_ONCE(ret != 0); goto retry;
} if (ret != 1) {
VM_WARN_ON_ONCE(ret > 1); if (!pages_done)
pages_done = ret; break;
}
nr_pages--;
pages_done++; if (!nr_pages) break; if (likely(pages))
pages++;
start += PAGE_SIZE;
} if (must_unlock && *locked) { /* * We either temporarily dropped the lock, or the caller * requested that we both acquire and drop the lock. Either way, * we must now unlock, and notify the caller of that state.
*/
mmap_read_unlock(mm);
*locked = 0;
}
/* * Failing to pin anything implies something has gone wrong (except when * FOLL_NOWAIT is specified).
*/ if (WARN_ON_ONCE(pages_done == 0 && !(flags & FOLL_NOWAIT))) return -EFAULT;
return pages_done;
}
/** * populate_vma_page_range() - populate a range of pages in the vma. * @vma: target vma * @start: start address * @end: end address * @locked: whether the mmap_lock is still held * * This takes care of mlocking the pages too if VM_LOCKED is set. * * Return either number of pages pinned in the vma, or a negative error * code on error. * * vma->vm_mm->mmap_lock must be held. * * If @locked is NULL, it may be held for read or write and will * be unperturbed. * * If @locked is non-NULL, it must held for read only and may be * released. If it's released, *@locked will be set to 0.
*/ long populate_vma_page_range(struct vm_area_struct *vma, unsignedlong start, unsignedlong end, int *locked)
{ struct mm_struct *mm = vma->vm_mm; unsignedlong nr_pages = (end - start) / PAGE_SIZE; int local_locked = 1; int gup_flags; long ret;
/* * Rightly or wrongly, the VM_LOCKONFAULT case has never used * faultin_page() to break COW, so it has no work to do here.
*/ if (vma->vm_flags & VM_LOCKONFAULT) return nr_pages;
/* ... similarly, we've never faulted in PROT_NONE pages */ if (!vma_is_accessible(vma)) return -EFAULT;
gup_flags = FOLL_TOUCH; /* * We want to touch writable mappings with a write fault in order * to break COW, except for shared mappings because these don't COW * and we would not want to dirty them for nothing. * * Otherwise, do a read fault, and use FOLL_FORCE in case it's not * readable (ie write-only or executable).
*/ if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
gup_flags |= FOLL_WRITE; else
gup_flags |= FOLL_FORCE;
if (locked)
gup_flags |= FOLL_UNLOCKABLE;
/* * We made sure addr is within a VMA, so the following will * not result in a stack expansion that recurses back here.
*/
ret = __get_user_pages(mm, start, nr_pages, gup_flags,
NULL, locked ? locked : &local_locked);
lru_add_drain(); return ret;
}
/* * faultin_page_range() - populate (prefault) page tables inside the * given range readable/writable * * This takes care of mlocking the pages, too, if VM_LOCKED is set. * * @mm: the mm to populate page tables in * @start: start address * @end: end address * @write: whether to prefault readable or writable * @locked: whether the mmap_lock is still held * * Returns either number of processed pages in the MM, or a negative error * code on error (see __get_user_pages()). Note that this function reports * errors related to VMAs, such as incompatible mappings, as expected by * MADV_POPULATE_(READ|WRITE). * * The range must be page-aligned. * * mm->mmap_lock must be held. If it's released, *@locked will be set to 0.
*/ long faultin_page_range(struct mm_struct *mm, unsignedlong start, unsignedlong end, bool write, int *locked)
{ unsignedlong nr_pages = (end - start) / PAGE_SIZE; int gup_flags; long ret;
/* * FOLL_TOUCH: Mark page accessed and thereby young; will also mark * the page dirty with FOLL_WRITE -- which doesn't make a * difference with !FOLL_FORCE, because the page is writable * in the page table. * FOLL_HWPOISON: Return -EHWPOISON instead of -EFAULT when we hit * a poisoned page. * !FOLL_FORCE: Require proper access permissions.
*/
gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE |
FOLL_MADV_POPULATE; if (write)
gup_flags |= FOLL_WRITE;
/* * __mm_populate - populate and/or mlock pages within a range of address space. * * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap * flags. VMAs must be already marked with the desired vm_flags, and * mmap_lock must not be held.
*/ int __mm_populate(unsignedlong start, unsignedlong len, int ignore_errors)
{ struct mm_struct *mm = current->mm; unsignedlong end, nstart, nend; struct vm_area_struct *vma = NULL; int locked = 0; long ret = 0;
end = start + len;
for (nstart = start; nstart < end; nstart = nend) { /* * We want to fault in pages for [nstart; end) address range. * Find first corresponding VMA.
*/ if (!locked) {
locked = 1;
mmap_read_lock(mm);
vma = find_vma_intersection(mm, nstart, end);
} elseif (nstart >= vma->vm_end)
vma = find_vma_intersection(mm, vma->vm_end, end);
if (!vma) break; /* * Set [nstart; nend) to intersection of desired address * range with the first VMA. Also, skip undesirable VMA types.
*/
nend = min(end, vma->vm_end); if (vma->vm_flags & (VM_IO | VM_PFNMAP)) continue; if (nstart < vma->vm_start)
nstart = vma->vm_start; /* * Now fault in a range of pages. populate_vma_page_range() * double checks the vma flags, so that it won't mlock pages * if the vma was already munlocked.
*/
ret = populate_vma_page_range(vma, nstart, nend, &locked); if (ret < 0) { if (ignore_errors) {
ret = 0; continue; /* continue at next VMA */
} break;
}
nend = nstart + ret * PAGE_SIZE;
ret = 0;
} if (locked)
mmap_read_unlock(mm); return ret; /* 0 or negative error code */
} #else/* CONFIG_MMU */ staticlong __get_user_pages_locked(struct mm_struct *mm, unsignedlong start, unsignedlong nr_pages, struct page **pages, int *locked, unsignedint foll_flags)
{ struct vm_area_struct *vma; bool must_unlock = false;
vm_flags_t vm_flags; long i;
if (!nr_pages) return 0;
/* * The internal caller expects GUP to manage the lock internally and the * lock must be released when this returns.
*/ if (!*locked) { if (mmap_read_lock_killable(mm)) return -EAGAIN;
must_unlock = true;
*locked = 1;
}
/* calculate required read or write permissions. * If FOLL_FORCE is set, we only require the "MAY" flags.
*/
vm_flags = (foll_flags & FOLL_WRITE) ?
(VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
vm_flags &= (foll_flags & FOLL_FORCE) ?
(VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
for (i = 0; i < nr_pages; i++) {
vma = find_vma(mm, start); if (!vma) break;
/* protect what we can, including chardevs */ if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) ||
!(vm_flags & vma->vm_flags)) break;
if (pages) {
pages[i] = virt_to_page((void *)start); if (pages[i])
get_page(pages[i]);
}
start = (start + PAGE_SIZE) & PAGE_MASK;
}
if (must_unlock && *locked) {
mmap_read_unlock(mm);
*locked = 0;
}
return i ? : -EFAULT;
} #endif/* !CONFIG_MMU */
/** * fault_in_writeable - fault in userspace address range for writing * @uaddr: start of address range * @size: size of address range * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()).
*/
size_t fault_in_writeable(char __user *uaddr, size_t size)
{ constunsignedlong start = (unsignedlong)uaddr; constunsignedlong end = start + size; unsignedlong cur;
if (unlikely(size == 0)) return 0; if (!user_write_access_begin(uaddr, size)) return size;
/* Stop once we overflow to 0. */ for (cur = start; cur && cur < end; cur = PAGE_ALIGN_DOWN(cur + PAGE_SIZE))
unsafe_put_user(0, (char __user *)cur, out);
out:
user_write_access_end(); if (size > cur - start) return size - (cur - start); return 0;
}
EXPORT_SYMBOL(fault_in_writeable);
/** * fault_in_subpage_writeable - fault in an address range for writing * @uaddr: start of address range * @size: size of address range * * Fault in a user address range for writing while checking for permissions at * sub-page granularity (e.g. arm64 MTE). This function should be used when * the caller cannot guarantee forward progress of a copy_to_user() loop. * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()).
*/
size_t fault_in_subpage_writeable(char __user *uaddr, size_t size)
{
size_t faulted_in;
/* * Attempt faulting in at page granularity first for page table * permission checking. The arch-specific probe_subpage_writeable() * functions may not check for this.
*/
faulted_in = size - fault_in_writeable(uaddr, size); if (faulted_in)
faulted_in -= probe_subpage_writeable(uaddr, faulted_in);
/* * fault_in_safe_writeable - fault in an address range for writing * @uaddr: start of address range * @size: length of address range * * Faults in an address range for writing. This is primarily useful when we * already know that some or all of the pages in the address range aren't in * memory. * * Unlike fault_in_writeable(), this function is non-destructive. * * Note that we don't pin or otherwise hold the pages referenced that we fault * in. There's no guarantee that they'll stay in memory for any duration of * time. * * Returns the number of bytes not faulted in, like copy_to_user() and * copy_from_user().
*/
size_t fault_in_safe_writeable(constchar __user *uaddr, size_t size)
{ constunsignedlong start = (unsignedlong)uaddr; constunsignedlong end = start + size; unsignedlong cur; struct mm_struct *mm = current->mm; bool unlocked = false;
if (unlikely(size == 0)) return 0;
mmap_read_lock(mm); /* Stop once we overflow to 0. */ for (cur = start; cur && cur < end; cur = PAGE_ALIGN_DOWN(cur + PAGE_SIZE)) if (fixup_user_fault(mm, cur, FAULT_FLAG_WRITE, &unlocked)) break;
mmap_read_unlock(mm);
if (size > cur - start) return size - (cur - start); return 0;
}
EXPORT_SYMBOL(fault_in_safe_writeable);
/** * fault_in_readable - fault in userspace address range for reading * @uaddr: start of user address range * @size: size of user address range * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()).
*/
size_t fault_in_readable(constchar __user *uaddr, size_t size)
{ constunsignedlong start = (unsignedlong)uaddr; constunsignedlong end = start + size; unsignedlong cur; volatilechar c;
if (unlikely(size == 0)) return 0; if (!user_read_access_begin(uaddr, size)) return size;
/* Stop once we overflow to 0. */ for (cur = start; cur && cur < end; cur = PAGE_ALIGN_DOWN(cur + PAGE_SIZE))
unsafe_get_user(c, (constchar __user *)cur, out);
out:
user_read_access_end();
(void)c; if (size > cur - start) return size - (cur - start); return 0;
}
EXPORT_SYMBOL(fault_in_readable);
/** * get_dump_page() - pin user page in memory while writing it to core dump * @addr: user address * @locked: a pointer to an int denoting whether the mmap sem is held * * Returns struct page pointer of user page pinned for dump, * to be freed afterwards by put_page(). * * Returns NULL on any kind of failure - a hole must then be inserted into * the corefile, to preserve alignment with its headers; and also returns * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - * allowing a hole to be left in the corefile to save disk space. * * Called without mmap_lock (takes and releases the mmap_lock by itself).
*/ #ifdef CONFIG_ELF_CORE struct page *get_dump_page(unsignedlong addr, int *locked)
{ struct page *page; int ret;
/* * An array of either pages or folios ("pofs"). Although it may seem tempting to * avoid this complication, by simply interpreting a list of folios as a list of * pages, that approach won't work in the longer term, because eventually the * layouts of struct page and struct folio will become completely different. * Furthermore, this pof approach avoids excessive page_folio() calls.
*/ struct pages_or_folios { union { struct page **pages; struct folio **folios; void **entries;
}; bool has_folios; long nr_entries;
};
staticstruct folio *pofs_get_folio(struct pages_or_folios *pofs, long i)
{ if (pofs->has_folios) return pofs->folios[i]; return page_folio(pofs->pages[i]);
}
for (; i < pofs->nr_entries; i++) { unsignedlong pfn = page_to_pfn(pofs->pages[i]);
/* Is this page part of this folio? */ if (pfn < start_pfn || pfn >= end_pfn) break;
}
}
if (unlikely(i == pofs->nr_entries)) return NULL;
*index_ptr = i;
return pofs_get_folio(pofs, i);
}
/* * Returns the number of collected folios. Return value is always >= 0.
*/ staticunsignedlong collect_longterm_unpinnable_folios( struct list_head *movable_folio_list, struct pages_or_folios *pofs)
{ unsignedlong collected = 0; struct folio *folio; int drained = 0; long i = 0;
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.